Training in progress, step 900

{checkpoint-600 → checkpoint-900}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94e544ed6fc2d04d9e3d9655de3eea506999b2814daab419e0d050c27a4a370f
+oid sha256:586c6f70f453bacaef539f6082450d1d6345b28afac567b5164059be9e21c0aa
 size 2490337809

{checkpoint-600 → checkpoint-900}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3baffe7a116d58666fc0726fb4fa6188834614eac15e96843270fc53529b943e
+oid sha256:704e6898ee156f5080bd3c12729eab90778262ef46c752641e041495f274ba56
 size 1262063089

{checkpoint-600 → checkpoint-900}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f58a88b760d3a9745a43789af262417186d48a5e0a471e8a2a080c8b3681cf9a
-size 14567
+oid sha256:9eb48c4b47c267134052f2e43cc544a219534620acef82e17a3e9be9f1684520
+size 14503

{checkpoint-600 → checkpoint-900}/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e8415b86bbce347c0df306b84a695add049c2a3b2d0b6f4dda3bf036d341150
+oid sha256:e8695f57df923e22b943b0b0f2b9cc7007008e80b53ccee275b3a35963fe67e9
 size 559

{checkpoint-600 → checkpoint-900}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6b4eb516015852d76c10d5b0c139cec1e488aa3b53e560bc99f9c2300e33423
+oid sha256:30116330e344473afc42b675f3adc8ae4b90035dba726f931014800aa6aa5856
 size 623

{checkpoint-600 → checkpoint-900}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.590163934426229,
-  "global_step": 600,
+  "epoch": 9.885245901639344,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -240,11 +240,128 @@
       "eval_steps_per_second": 0.785,
       "eval_wer": 1.0,
       "step": 600
+    },
+    {
+      "epoch": 6.81,
+      "learning_rate": 7.75e-05,
+      "loss": 2.9921,
+      "step": 620
+    },
+    {
+      "epoch": 7.03,
+      "learning_rate": 8e-05,
+      "loss": 3.0665,
+      "step": 640
+    },
+    {
+      "epoch": 7.25,
+      "learning_rate": 8.25e-05,
+      "loss": 2.9826,
+      "step": 660
+    },
+    {
+      "epoch": 7.47,
+      "learning_rate": 8.5e-05,
+      "loss": 2.9689,
+      "step": 680
+    },
+    {
+      "epoch": 7.69,
+      "learning_rate": 8.75e-05,
+      "loss": 2.9602,
+      "step": 700
+    },
+    {
+      "epoch": 7.69,
+      "eval_loss": 2.9620397090911865,
+      "eval_runtime": 193.5851,
+      "eval_samples_per_second": 25.017,
+      "eval_steps_per_second": 0.785,
+      "eval_wer": 1.0,
+      "step": 700
+    },
+    {
+      "epoch": 7.91,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 2.9639,
+      "step": 720
+    },
+    {
+      "epoch": 8.13,
+      "learning_rate": 9.25e-05,
+      "loss": 3.0215,
+      "step": 740
+    },
+    {
+      "epoch": 8.35,
+      "learning_rate": 9.5e-05,
+      "loss": 2.9454,
+      "step": 760
+    },
+    {
+      "epoch": 8.57,
+      "learning_rate": 9.750000000000001e-05,
+      "loss": 2.9239,
+      "step": 780
+    },
+    {
+      "epoch": 8.79,
+      "learning_rate": 0.0001,
+      "loss": 2.8756,
+      "step": 800
+    },
+    {
+      "epoch": 8.79,
+      "eval_loss": 2.7302000522613525,
+      "eval_runtime": 191.8065,
+      "eval_samples_per_second": 25.249,
+      "eval_steps_per_second": 0.792,
+      "eval_wer": 1.0,
+      "step": 800
+    },
+    {
+      "epoch": 9.01,
+      "learning_rate": 0.0001025,
+      "loss": 2.8933,
+      "step": 820
+    },
+    {
+      "epoch": 9.23,
+      "learning_rate": 0.000105,
+      "loss": 2.7318,
+      "step": 840
+    },
+    {
+      "epoch": 9.45,
+      "learning_rate": 0.0001075,
+      "loss": 2.5941,
+      "step": 860
+    },
+    {
+      "epoch": 9.67,
+      "learning_rate": 0.00011,
+      "loss": 2.4441,
+      "step": 880
+    },
+    {
+      "epoch": 9.89,
+      "learning_rate": 0.00011250000000000001,
+      "loss": 2.2931,
+      "step": 900
+    },
+    {
+      "epoch": 9.89,
+      "eval_loss": 1.5057899951934814,
+      "eval_runtime": 196.4368,
+      "eval_samples_per_second": 24.654,
+      "eval_steps_per_second": 0.774,
+      "eval_wer": 0.9775759296054499,
+      "step": 900
     }
   ],
   "max_steps": 4550,
   "num_train_epochs": 50,
-  "total_flos": 9.32024224555606e+18,
+  "total_flos": 1.3944116272848585e+19,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83f2151485570eebb9c2c7ead79b5dbb947c911745136ec08aec4531150fc59d
+oid sha256:704e6898ee156f5080bd3c12729eab90778262ef46c752641e041495f274ba56
 size 1262063089